Skip to main content
Kent Academic Repository

Flow Pattern Recognition of CO2 Gas-Liquid Two-Phase Flow Based on Texture Features of Gray-Level Co-occurrence Matrix

Zhang, Yukun, Sun, Caiying, Wang, Lijuan, Zhang, Zhen (2026) Flow Pattern Recognition of CO2 Gas-Liquid Two-Phase Flow Based on Texture Features of Gray-Level Co-occurrence Matrix. In: 2026 IEEE International Instrumentation and Measurement Technology Conference. IEEE E-ISBN 979-8-3315-8938-7. (doi:10.1109/I2MTC66907.2026.11694422) (KAR id:113886)

Abstract

In the field of carbon capture and storage (CCS), accurate recognition of flow patterns in CO2 gas-liquid two-phase flow is crucial for mass flow rate measurement. This paper presents a flow pattern recognition method based on texture features of gray level co-occurrence matrix (GLCM). This method extracts four GLCM texture features by preprocessing flow pattern images to generate feature vectors, and then uses support vector machine (SVM) model to distinguish three flow patterns in CO2 gas-liquid two-phase flow: stratified flow, bubbly flow, and mist flow. The experimental results confirm that the proposed method achieves a classification accuracy of 98.14%. The SVM model demonstrates an advantage over both least squares support vector machine (LSSVM) and Back Propagation Neural Network (BPNN) models. This paper provides an accurate and efficient solution for flow pattern recognition in CO2 gas-liquid two-phase flow.

Item Type: Conference proceeding
DOI/Identification number: 10.1109/I2MTC66907.2026.11694422
Additional information: For the purpose of open access, the author(s) has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising.
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA165 Engineering instruments, meters etc. Industrial instrumentation
Institutional Unit: Schools > School of Engineering, Mathematics and Physics > Engineering
Former Institutional Unit:
There are no former institutional units.
Funders: University of Kent (https://ror.org/00xkeyj56)
Depositing User: Lijuan Wang
Date Deposited: 15 Apr 2026 16:18 UTC
Last Modified: 28 Oct 2026 04:10 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/113886 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views of this page since July 2020. For more details click on the image.